© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 42009
    Prev
    Next
    INDEX
    Explanations

    references to actions related to returning, coming back, or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.32
    2:0.03
    3:0.04
    4:0.03
    5:0.20
    6:0.03
    7:0.01
    8:0.06
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    イト
    -2.07
    Pl
    -1.88
    Creat
    -1.77
    Iv
    -1.76
    ICE
    -1.70
    IV
    -1.70
    ihad
    -1.68
     Amph
    -1.68
    oran
    -1.65
    �
    -1.64
    POSITIVE LOGITS
     backward
    2.12
    anwhile
    2.11
     BACK
    2.04
     goodbye
    1.91
     rall
    1.89
     back
    1.83
     awa
    1.78
     Back
    1.77
    back
    1.75
     backdoor
    1.74
    Activations Density 0.004%

    No Known Activations